Enum EmbeddingModel 

pub enum EmbeddingModel {
    AllMiniLML6V2,
    AllMiniLML12V2,
    AllMpnetBaseV2,
    BGESmallENV15,
    BGEBaseENV15,
    BGELargeENV15,
    BGESmallZHV15,
    BGELargeZHV15,
    MultilingualE5Small,
    MultilingualE5Base,
    MultilingualE5Large,
    ParaphraseMLMiniLML12V2,
    ParaphraseMLMpnetBaseV2,
    SnowflakeArcticEmbedXS,
    SnowflakeArcticEmbedS,
    SnowflakeArcticEmbedM,
    SnowflakeArcticEmbedL,
    MxbaiEmbedLargeV1,
    NomicEmbedTextV15,
}

Supported text embedding models.

Each variant maps to a specific HuggingFace model repository with pre-trained safetensors weights. Use EmbeddingModel::get_info to access metadata (dimension, pooling strategy, max sequence length).

Variants

AllMiniLML6V2

sentence-transformers/all-MiniLM-L6-v2 — 384-dim, 6 layers, mean pooling.

AllMiniLML12V2

sentence-transformers/all-MiniLM-L12-v2 — 384-dim, 12 layers, mean pooling.

AllMpnetBaseV2

sentence-transformers/all-mpnet-base-v2 — 768-dim, 12 layers, mean pooling. Note: mpnet architecture — uses different attention key naming.

BGESmallENV15

BAAI/bge-small-en-v1.5 — 384-dim, 12 layers, CLS pooling.

BGEBaseENV15

BAAI/bge-base-en-v1.5 — 768-dim, 12 layers, CLS pooling.

BGELargeENV15

BAAI/bge-large-en-v1.5 — 1024-dim, 24 layers, CLS pooling.

BGESmallZHV15

BAAI/bge-small-zh-v1.5 — 512-dim, 12 layers, CLS pooling.

BGELargeZHV15

BAAI/bge-large-zh-v1.5 — 1024-dim, 24 layers, CLS pooling.

MultilingualE5Small

intfloat/multilingual-e5-small — 384-dim, 12 layers, mean pooling.

MultilingualE5Base

intfloat/multilingual-e5-base — 768-dim, 12 layers, mean pooling.

MultilingualE5Large

intfloat/multilingual-e5-large — 1024-dim, 24 layers, mean pooling.

ParaphraseMLMiniLML12V2

sentence-transformers/paraphrase-multilingual-MiniLM-L12-v2 — 384-dim, 12 layers, mean pooling.

ParaphraseMLMpnetBaseV2

sentence-transformers/paraphrase-multilingual-mpnet-base-v2 — 768-dim, 12 layers, mean pooling.

SnowflakeArcticEmbedXS

snowflake/snowflake-arctic-embed-xs — 384-dim, CLS pooling.

SnowflakeArcticEmbedS

snowflake/snowflake-arctic-embed-s — 384-dim, CLS pooling.

SnowflakeArcticEmbedM

Snowflake/snowflake-arctic-embed-m — 768-dim, CLS pooling.

SnowflakeArcticEmbedL

snowflake/snowflake-arctic-embed-l — 1024-dim, CLS pooling.

MxbaiEmbedLargeV1

mixedbread-ai/mxbai-embed-large-v1 — 1024-dim, CLS pooling.

NomicEmbedTextV15

nomic-ai/nomic-embed-text-v1.5 — 768-dim, 12 layers, mean pooling, RoPE, SwiGLU.

Implementations

impl EmbeddingModel

pub fn get_info(&self) -> Option<&'static ModelInfo>

Look up metadata for this model.

pub fn list_supported() -> Vec<&'static ModelInfo>

List all supported models.

Trait Implementations

impl Clone for EmbeddingModel

fn clone(&self) -> EmbeddingModel

Returns a duplicate of the value.

fn clone_from(&mut self, source: &Self)

Performs copy-assignment from source.

impl Debug for EmbeddingModel

fn fmt(&self, f: &mut Formatter<'_>) -> Result

Formats the value using the given formatter.

impl Default for EmbeddingModel

fn default() -> EmbeddingModel

Returns the “default value” for a type.

impl Eq for EmbeddingModel

impl Hash for EmbeddingModel

fn hash<__H: Hasher>(&self, state: &mut __H)

Feeds this value into the given Hasher.

fn hash_slice<H>(data: &[Self], state: &mut H)

where H: Hasher, Self: Sized,

Feeds a slice of this type into the given Hasher.

impl PartialEq for EmbeddingModel

fn eq(&self, other: &EmbeddingModel) -> bool

Tests for self and other values to be equal, and is used by ==.

fn ne(&self, other: &Rhs) -> bool

Tests for !=. The default implementation is almost always sufficient, and should not be overridden without very good reason.

impl StructuralPartialEq for EmbeddingModel